Clonal selection algorithm for energy minimization in software defined networks

Mir Wajahat Hussain

doi:10.1016/j.asoc.2020.106617

2020-11-01

PRE

Mir Wajahat Hussain

Buddhadeb Pradhan

Xiao‐Zhi Gao

K. Hemant Kumar Reddy

Diptendu Sinha Roy *

DOI：10.1016/j.asoc.2020.106617

原文链接

摘要

En 中文

With the advancements of Information and Communication Technologies (ICT), large scale distributed computing and massive data center infrastructures are becoming more common these days. Such trends have drastically put a lot of load on the volumes of data transferred over networks, thus necessitating close to capacity link utilizations flexible forwarding decision-making. Software-defined networking (SDN), with its inherent segregation of control and data planes, provides flexible decision making that can leverage the global network information available to the SDN controller for dynamic and accurate solutions. However, contemporary researchers have focused on the flexibility and security aspects of SDN, widely ignoring energy consumption strategies in next-generation IP networks, which otherwise is a crucial driver in any research field. The scanty existing energy minimization strategies are mostly based on aggregate traffic, which leads to imbalanced utilization of links and affects the quality of service (QoS) adversely. In this paper, we leverage SDN's key benefits for reducing energy network consumption while realizing dynamic load balance with a few QoS constraints. To this end, a multiobjective optimization problem (MOOP) is formulated that attempts to minimize power consumption and link utilization. With different capacities of switches and links, finding optimal configurations and deciding best paths, even for relatively small networks, become computationally challenging and is, in fact, an NP-hard problem. In this paper, we propose to employ the Clonal Selection Algorithm (CSA), a discrete, metaheuristic solution to find out optimal solutions for this MOOP, namely a Clonal Selection based Energy Minimization (CSEM). Simulations have been carried out for testing the efficacy of the proposed CSEM using real-life network topologies and link-traffic data. The results obtained by the proposed CSEM prove to be efficacious, and the same have also been validated with three different benchmark functions to test the suitability of SDN for CSA. (C) 2020 Elsevier B.V. All rights reserved.

Keyword:

Software-defined networking (SDN)

Clonal Selection Algorithm (CSA)

Load balancing

Energy optimization